OpenTeller
Private budgeting for any bank, in the AI you already use
What it does
Most budgeting apps reach your bank through an aggregator, and the free ones pay for that access by profiling what you spend. OpenTeller has no middleman. You log into your bank inside the app, train it once, then sync in one tap. Any bank, any country, credentials never leaving your device. In no account mode, your data sits encrypted in your own iCloud. Categorization runs on Apple Intelligence, on-device. You can bring your own AI. An MCP endpoint lets Claude and ChatGPT read your data
Plan your budget with any bank in the world. Set a limit per category, pull transactions in with one-tap sync, a CSV, or a screenshot, and never share your bank password.
Set a limit for every category and watch it track itself. Bring transactions in with one-tap sync, a CSV, or a screenshot, without ever sharing your bank password. Clean categories, budgets, trends. Plus an AI assistant that answers from your real data. Most finance apps make you connect your bank account. Here's why that causes trouble. Traditional apps only connect to a select few major banks. If you use a local credit union, regional bank, or an international account, you're usually out of luck. Tired of your accounts constantly disconnecting? Security updates on other apps force you to log back in and re-link your bank every few weeks just to see your data. Handing your bank password…from openteller.app
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com